© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-4B
    3. 22-TRANSCODER-HP
    4. 112404
    Prev
    Next
    INDEX
    Explanations

    Terms of service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elm
    -0.26
    ê°ij
    -0.25
    æĬij
    -0.25
    ê°Ŀ
    -0.25
    åijĬè¯ī
    -0.24
    éĥ½è¯´
    -0.24
    æĤĥ
    -0.24
    iss
    -0.24
    è¿ĺ以为
    -0.23
    Yes
    -0.23
    POSITIVE LOGITS
    avn
    0.31
     livest
    0.25
    ibri
    0.25
    ricular
    0.24
    apy
    0.24
    aping
    0.23
    icap
    0.23
    åĢŁç͍
    0.23
     retrie
    0.23
    icals
    0.23
    Activations Density 0.005%

    No Known Activations